PREDICTIONS OF COLLEGE STUDENTS’ MENTAL STRESS USING MACHINE LEARNING ALGORITHMS

Abstract

The mental health of college students has become a significant concern, with increasing awareness of stress and its impact on academic performance and overall well-being. Early efforts in this area used surveys and counseling sessions to identify stress levels. Traditional System Surveys and Questionnaires, Interviews and Counseling Sessions, Observational Methods Academic Performance and Attendance Records, Problem Statement: College students experience high levels of stress, but existing mental health support systems are reactive and fail to provide timely interventions. There is a need for accurate, real-time prediction models to identify and address mental stress early. Research Motivation like Machine learning algorithms offer the potential to predict mental stress with higher accuracy and timeliness. This research aims to develop predictive models to identify stress patterns and enable early interventions, thereby improving student well-being.The proposed system leverages machine learning algorithms to predict mental stress among college students based on various factors such as academic performance, social interactions, and physiological data. The system aims to provide real-time stress level predictions, allowing for early and targeted interventions. Like Stress Sense, Smartphone-Based Stress Monitoring, EduWell is a comprehensive system that integrates academic performance, attendance records, and self-reported data to predict student stress levels, WellBe is a smart bracelet that monitors physiological parameters such as heart rate and skin temperature to assess stress levels. It utilizes classification models like Random Forest and SVM for accurate predictions and effective stress management.